{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2012.05208","title":"On the Binding Problem in Artificial Neural Networks","created":"2020-12-09","cited_by_count":233},{"id":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187},{"id":"2206.07764","title":"SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videos","created":"2022-06-15","cited_by_count":166},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147},{"id":"1612.06370","title":"Learning Features by Watching Objects Move","created":"2016-12-19","cited_by_count":138},{"id":"2209.00383","title":"TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut","created":"2022-09-01","cited_by_count":113},{"id":"2202.12181","title":"FreeSOLO: Learning to Segment Objects without Annotations","created":"2022-02-24","cited_by_count":102},{"id":"1810.06125","title":"Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding","created":"2018-10-14","cited_by_count":101},{"id":"2010.16404","title":"Unsupervised Monocular Depth Learning in Dynamic Scenes","created":"2020-10-30","cited_by_count":84},{"id":"1612.04402","title":"Finding Tiny Faces","created":"2016-12-13","cited_by_count":72},{"id":"1501.06170","title":"Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals","created":"2015-01-25","cited_by_count":69},{"id":"2212.07834","title":"Unsupervised Object Localization: Observing the Background to Discover Objects","created":"2022-12-15","cited_by_count":66},{"id":"2007.02662","title":"Toward unsupervised, multi-object discovery in large-scale image collections","created":"2020-07-06","cited_by_count":65},{"id":"2011.11630","title":"Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation","created":"2020-11-23","cited_by_count":62},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58},{"id":"1908.04051","title":"Semi-Supervised Video Salient Object Detection Using Pseudo-Labels","created":"2019-08-12","cited_by_count":54},{"id":"2106.06650","title":"Large-Scale Unsupervised Object Discovery","created":"2021-06-12","cited_by_count":54},{"id":"2206.06363","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","created":"2022-06-13","cited_by_count":54},{"id":"1904.09172","title":"Video Object Segmentation and Tracking: A Survey","created":"2019-04-19","cited_by_count":50},{"id":"2310.06907","title":"Self-supervised Object-Centric Learning for Videos","created":"2023-10-10","cited_by_count":49},{"id":"2203.10159","title":"Discovering Objects that Can Move","created":"2022-03-18","cited_by_count":44},{"id":"2203.15882","title":"Learning to Detect Mobile Objects from LiDAR Scans Without Labels","created":"2022-03-29","cited_by_count":44},{"id":"1904.03148","title":"Unsupervised Image Matching and Object Discovery as Optimization","created":"2019-04-05","cited_by_count":42},{"id":"2003.05020","title":"Learning Video Object Segmentation from Unlabeled Videos","created":"2020-03-10","cited_by_count":42},{"id":"2205.07844","title":"Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion","created":"2022-05-16","cited_by_count":42},{"id":"1812.02772","title":"Object Discovery in Videos as Foreground Motion Clustering","created":"2018-12-06","cited_by_count":32},{"id":"2110.06562","title":"Unsupervised Object Learning via Common Fate","created":"2021-10-13","cited_by_count":29},{"id":"2007.12348","title":"Unsupervised Discovery of 3D Physical Objects from Video","created":"2020-07-24","cited_by_count":27},{"id":"2011.12953","title":"Unsupervised Object Detection with LiDAR Clues","created":"2020-11-25","cited_by_count":22},{"id":"2303.04456","title":"RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes","created":"2023-03-08","cited_by_count":22},{"id":"2104.04782","title":"Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation","created":"2021-04-10","cited_by_count":21},{"id":"2310.18887","title":"Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes","created":"2023-10-29","cited_by_count":20},{"id":"1505.03825","title":"Unsupervised Object Discovery and Tracking in Video Collections","created":"2015-05-14","cited_by_count":17},{"id":"1703.10901","title":"Unsupervised learning from video to detect foreground objects in single images","created":"2017-03-31","cited_by_count":15},{"id":"2304.08025","title":"Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping","created":"2023-04-17","cited_by_count":15},{"id":"2402.03311","title":"HASSOD: Hierarchical Adaptive Self-Supervised Object Detection","created":"2024-02-05","cited_by_count":10},{"id":"2308.11239","title":"LOCATE: Self-supervised Object Discovery via Flow-guided Graph-cut and Bootstrapped Self-training","created":"2023-08-22","cited_by_count":8},{"id":"2307.04392","title":"FODVid: Flow-guided Object Discovery in Videos","created":"2023-07-10","cited_by_count":3}],"next_cursor":null}